Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection
In the recent research era, artificial intelligence techniques have been used for computer vision, big data analysis, and detection systems. The development of these advanced technologies has also increased security and privacy issues. One kind of this issue is Deepfakes which is the combined word o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2022-07-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1040.pdf |
| _version_ | 1818529204451409920 |
|---|---|
| author | Saravana Balaji Balasubramanian Jagadeesh Kannan R Prabu P Venkatachalam K Pavel Trojovský |
| author_facet | Saravana Balaji Balasubramanian Jagadeesh Kannan R Prabu P Venkatachalam K Pavel Trojovský |
| author_sort | Saravana Balaji Balasubramanian |
| collection | DOAJ |
| description | In the recent research era, artificial intelligence techniques have been used for computer vision, big data analysis, and detection systems. The development of these advanced technologies has also increased security and privacy issues. One kind of this issue is Deepfakes which is the combined word of deep learning and fake. DeepFake refers to the formation of a fake image or video using artificial intelligence approaches which are created for political abuse, fake data transfer, and pornography. This paper has developed a Deepfake detection method by examining the computer vision features of the digital content. The computer vision features based on the frame change are extracted using a proposed deep learning model called the Cascaded Deep Sparse Auto Encoder (CDSAE) trained by temporal CNN. The detection process is performed using a Deep Neural Network (DNN) to classify the deep fake image/video from the real image/video. The proposed model is implemented using Face2Face, FaceSwap, and DFDC datasets which have secured an improved detection rate when compared to the traditional deep fake detection approaches. |
| first_indexed | 2024-12-11T17:03:56Z |
| format | Article |
| id | doaj.art-571ef014727a481cbd595bf2e247e166 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-11T17:03:56Z |
| publishDate | 2022-07-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-571ef014727a481cbd595bf2e247e1662022-12-22T00:57:45ZengPeerJ Inc.PeerJ Computer Science2376-59922022-07-018e104010.7717/peerj-cs.1040Deep fake detection using cascaded deep sparse auto-encoder for effective feature selectionSaravana Balaji Balasubramanian0Jagadeesh Kannan R1Prabu P2Venkatachalam K3Pavel Trojovský4Department of Information Technology, Lebanese French University, Erbil, IraqSchool of Computer Science and Engineering, VIT Chennai, Chennai, Tamilnadu, IndiaDepartment of Computer Science, CHRIST (Deemed to be University), Bangalore, Karnataka, IndiaDepartment of Applied Cybernetics, University of Hradec Králové, Hradec Kralove, Czech RepublicDepartment of Mathematics, University of Hradec Králové, Hradec Kralove, Czech RepublicIn the recent research era, artificial intelligence techniques have been used for computer vision, big data analysis, and detection systems. The development of these advanced technologies has also increased security and privacy issues. One kind of this issue is Deepfakes which is the combined word of deep learning and fake. DeepFake refers to the formation of a fake image or video using artificial intelligence approaches which are created for political abuse, fake data transfer, and pornography. This paper has developed a Deepfake detection method by examining the computer vision features of the digital content. The computer vision features based on the frame change are extracted using a proposed deep learning model called the Cascaded Deep Sparse Auto Encoder (CDSAE) trained by temporal CNN. The detection process is performed using a Deep Neural Network (DNN) to classify the deep fake image/video from the real image/video. The proposed model is implemented using Face2Face, FaceSwap, and DFDC datasets which have secured an improved detection rate when compared to the traditional deep fake detection approaches.https://peerj.com/articles/cs-1040.pdfDeep fake detectionDeep learningDeep sparse Auto encoderTemporal Convolutional neural networkDNNFace2Face |
| spellingShingle | Saravana Balaji Balasubramanian Jagadeesh Kannan R Prabu P Venkatachalam K Pavel Trojovský Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection PeerJ Computer Science Deep fake detection Deep learning Deep sparse Auto encoder Temporal Convolutional neural network DNN Face2Face |
| title | Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection |
| title_full | Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection |
| title_fullStr | Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection |
| title_full_unstemmed | Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection |
| title_short | Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection |
| title_sort | deep fake detection using cascaded deep sparse auto encoder for effective feature selection |
| topic | Deep fake detection Deep learning Deep sparse Auto encoder Temporal Convolutional neural network DNN Face2Face |
| url | https://peerj.com/articles/cs-1040.pdf |
| work_keys_str_mv | AT saravanabalajibalasubramanian deepfakedetectionusingcascadeddeepsparseautoencoderforeffectivefeatureselection AT jagadeeshkannanr deepfakedetectionusingcascadeddeepsparseautoencoderforeffectivefeatureselection AT prabup deepfakedetectionusingcascadeddeepsparseautoencoderforeffectivefeatureselection AT venkatachalamk deepfakedetectionusingcascadeddeepsparseautoencoderforeffectivefeatureselection AT paveltrojovsky deepfakedetectionusingcascadeddeepsparseautoencoderforeffectivefeatureselection |